首页|Data on Machine Learning Reported by Researchers at McMaster University (Explain able Ensemble Learning Predictive Model for Thermal Conductivity of Cement-based Foam)
Data on Machine Learning Reported by Researchers at McMaster University (Explain able Ensemble Learning Predictive Model for Thermal Conductivity of Cement-based Foam)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Machine Learning have been presented. According to news reporting originating from Hamilton, Canada, by NewsRx correspondents, research stated, "Cement-based foam has emerged as a s trong contender in sustainable construction owing to its superior thermal and so und insulation properties, fire resistance, and cost-effectiveness. To effective ly use cement-based foam as a thermal insulation material, it is important to ac curately predict its thermal conductivity." Our news editors obtained a quote from the research from McMaster University, "T he current study aims at coining an accurate methodology for predicting the ther mal conductivity of cement-based foam using state-ofthe-art machine learning tec hniques. A comprehensive experimental dataset of 504 data points was developed a nd used for training ensemble learning models including XGBoost, CatBoost, Light GBM and Random Forest. The independent variables of this dataset affecting the t hermal conductivity are the cast density, percentage of pozzolan, porosity, perc entage of moisture, and duration of hydration in days. Using the Isolation Fores t algorithm proved effective in detecting and eliminating outliers in the datase t. All the ensemble learning techniques explored in this study achieved superior predictive accuracy with a coefficient of determination greater than 0.98 on th e test dataset. The influence of the input features on the thermal conductivity was visualized using the SHapley Additive exPlanations (SHAP) approach and indiv idual conditional expectation (ICE) plots. The cast density had the greatest eff ect on thermal conductivity."
HamiltonCanadaNorth and Central Amer icaCyborgsEmerging TechnologiesMachine LearningMcMaster University